Characteristics of Equinumber Principle for Adaptive Vector Quantization

This paper describes characteristics of adaptive vector quantization according to the equinumber principle. Three methods of adaptive vector quantization are presented with the objective of avoiding the initial dependency of reference vectors. The present approaches which have output units without neighboring relations equalize the numbers of inputs in a partition space. The first approach is a creation method which sequentially creates output units to reach a predetermined number of neurons founded on the equinumber principle in the learning process. The second is a reduction method which sequentially deletes output units to reach a prespecified number. The third is an unification method of the creation and reduction methods, which deletes units after creating under the predetermined number. Experimental results show the properties of the present techniques.

[1]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[2]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[3]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[4]  GrossbergS..  Adaptive pattern classification and universal recoding , 1976 .

[5]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[6]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[7]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[8]  Robert B. Ash,et al.  Information Theory , 2020, The SAGE International Encyclopedia of Mass Media and Society.

[9]  Allen Gersho,et al.  On the structure of vector quantizers , 1982, IEEE Trans. Inf. Theory.

[10]  Noritaka Shigei,et al.  Adaptive Vector Quantization with Creation and Reduction Grounded in the Equinumber Principle , 2005, J. Adv. Comput. Intell. Intell. Informatics.

[11]  Allen Gersho,et al.  Asymptotically optimal block quantization , 1979, IEEE Trans. Inf. Theory.

[12]  Paul L. Zador,et al.  Asymptotic quantization error of continuous signals and the quantization dimension , 1982, IEEE Trans. Inf. Theory.

[13]  S. Grossberg,et al.  Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors , 1976, Biological Cybernetics.

[14]  K. Schulten,et al.  On the stationary state of Kohonen's self-organizing sensory mapping , 2004, Biological Cybernetics.

[15]  L. Reichl.  A modern course in statistical physics , 1980 .

[16]  H. Ritter,et al.  Convergence properties of Kohonen's topology conserving maps: fluctuations, stability, and dimension selection , 1988, Biological Cybernetics.

[17]  C. Malsburg,et al.  How patterned neural connections can be set up by self-organization , 1976, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[18]  Saburo Tazaki,et al.  Asymptotic performance of block quantizers with difference distortion measures , 1980, IEEE Trans. Inf. Theory.